公开(公告)号：US20200057966A1

公开(公告)日：2020-02-20

申请号：US16105182

申请日：2018-08-20

Applicant: United Microelectronics Corp.

Inventor： Yao-Sheng Chang ,  Ya-Ching Cheng ,  Chien-Hung Chen ,  Chih-Yueh Li ,  Da-Ching Liao

IPC: G06N99/00 ,  G06F5/01 ,  G06F17/16

Abstract: A training apparatus and a training method for providing a sample size expanding model are provided. A normalizing unit receives a training data set with at least one numeric predictor factor and a numeric response factor. An encoding unit trains the training data set in an initial encoding layer and at least one deep encoding layer. A modeling unit extracts a mean vector and a variance vector and inputting the mean vector and the variance vector together into a latent hidden layer for obtaining the sample size expanding model. A decoding unit trains the training data set in at least one deep decoding layer and a last encoding layer. A verifying unit performs a verification of the sample size expanding model according to the outputting data set. A data generating unit generates a plurality of samples via the sample size expanding model.

公开(公告)号：US11461693B2

公开(公告)日：2022-10-04

申请号：US16105182

申请日：2018-08-20

Applicant: United Microelectronics Corp.

Inventor： Yao-Sheng Chang ,  Ya-Ching Cheng ,  Chien-Hung Chen ,  Chih-Yueh Li ,  Da-Ching Liao

IPC: G06N20/00 ,  G06F17/16 ,  G06F5/01

Abstract: A training apparatus and a training method for providing a sample size expanding model are provided. A normalizing unit receives a training data set with at least one numeric predictor factor and a numeric response factor. An encoding unit trains the training data set in an initial encoding layer and at least one deep encoding layer. A modeling unit extracts a mean vector and a variance vector and inputting the mean vector and the variance vector together into a latent hidden layer for obtaining the sample size expanding model. A decoding unit trains the training data set in at least one deep decoding layer and a last encoding layer. A verifying unit performs a verification of the sample size expanding model according to the outputting data set. A data generating unit generates a plurality of samples via the sample size expanding model.